Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1412 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.7346. Min Act: -0.0000

Data Index: 966357 (The Pile)

Max Activating Token Index: 301

Text #1

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1960975 (The Pile)

Max Activating Token Index: 891

Text #2

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1270227 (The Pile)

Max Activating Token Index: 292

Text #3

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6567. Min Act: -0.0000

Data Index: 572449 (The Pile)

Max Activating Token Index: 264

Text #4

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.5776. Min Act: -0.0000

Data Index: 875034 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.5805. Min Act: -0.0000

Data Index: 1528291 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1210677 (The Pile)

Max Activating Token Index: 571

Text #7

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1586908 (The Pile)

Max Activating Token Index: 697

Text #8

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1002685 (The Pile)

Max Activating Token Index: 123

Text #9

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.5348. Min Act: -0.0000

Data Index: 1292654 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.5321. Min Act: -0.0000

Data Index: 422511 (The Pile)

Max Activating Token Index: 185

Text #11

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.4731. Min Act: -0.0000

Data Index: 281764 (The Pile)

Max Activating Token Index: 221

Text #12

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.5210. Min Act: -0.0000

Data Index: 898189 (The Pile)

Max Activating Token Index: 786

Text #13

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1224571 (The Pile)

Max Activating Token Index: 792

Text #14

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.4344. Min Act: -0.0000

Data Index: 485248 (The Pile)

Max Activating Token Index: 808

Text #15

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1269378 (The Pile)

Max Activating Token Index: 361

Text #16

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1165052 (The Pile)

Max Activating Token Index: 798

Text #17

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.4756. Min Act: -0.0000

Data Index: 299820 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1159201 (The Pile)

Max Activating Token Index: 693

Text #19

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.4542. Min Act: -0.0000

Data Index: 419216 (The Pile)

Max Activating Token Index: 753